EmotiVoice

EmotiVoice copied to clipboard

如何调整生成的语速

5

我在prompt里用语速普通、语速很快和语速很慢发现区别不大，在代码里其他地方也没发现与速度相关的地方，请问有没有办法能调整生成的语音的语速

MisakaMikoto-o

这个项目是收费的还是免费的

1

这个项目是收费的还是免费的

AmorFat1

How to control the speech speed in openAPI

1

I am using fastAPI service and there is a `speed` field in the request body. I guess it can control the speed of the speech. But after several tests, the...

costanzo

是否可以支持自定义训练音色

1

当前音色读出来都是外国人读中文，一股奇特的味道

dup2X

Inquiry Regarding Missing datalist.jsonl File

1

I am currently using the Montreal Forced Aligner (MFA) for an audio processing task, following the instructions in the documentation. However, I've encountered an issue when trying to proceed with...

Ccj0221

tokens like uncased15 - uncased99 mean what?

3


huangxu1991

中英混合的如何做呢？Mixing Chinese and English leads to errors.

7

xxm1668

EmotiVoice/frontend.py", line 26, in split_py if py[-1] == 'r': IndexError: string index out of range

8

EmotiVoice/frontend.py", line 26, in split_py if py[-1] == 'r': IndexError: string index out of range 测试问题： ``` 抱歉刚刚的回答可能让你感到不满意了。作为一个大语言模型，我并不具备情感和自主意识，我的回答是基于大量的数据和算法生成的。如果我的回答有不准确或者不恰当的地方，还请您多多包涵和指教。 我是由百川智能的工程师们开发和维护的。他们是一群富有创造力和激情的人，致力于为我提供更好的服务和功能。 测试一下中英混合文本，hello,你好啊。Hello, this is the best test for now。我们很期待您的到来，希望你在这次盛会中得到你想要的结果。 ```

lucasjinreal

EmotiVoice/inference_am_vocoder_joint.py", line 66, in main style_encoder.load_state_dict(model_ckpt) File "/root/anaconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for StyleEncoder: Unexpected key(s) in state_dict: "bert.embeddings.position_ids".

7

EmotiVoice/inference_am_vocoder_joint.py", line 66, in main style_encoder.load_state_dict(model_ckpt) File "/root/anaconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for StyleEncoder: Unexpected key(s) in state_dict:...

lucasjinreal

请问有自带中国人声音的speaker吗

5

看了一下speaker列表似乎都是外国人？有中国人的speaker吗，还是说需要自己在哪里下载导入到什么地方，谢谢啦

richardjian2023